NVIDIA边缘AI芯片无法追踪单进程能耗，导致能效优化成空谈。
The Energy Blind Spot: NVIDIA's Flagship Edge AI Hardware Cannot Support Process-Level Energy Attribution
- 芯片无CPU功耗计数器，仅能读取GPU瞬时功耗
- 实测发现主板固件内部已计算各电源轨能耗但未开放接口
- 提出临时校准方案并呼吁建立标准能耗监控协议
面向边缘部署的智能体工作负载（Agentic AI）正成为主流，2026年包括NVIDIA、戴尔、惠普等厂商将推出基于GB10的桌面AI系统。已有研究显示，任务编排结构主导能耗，且CPU侧动态功耗占比高达44%。我们对ASUS Ascent GX10（GB10 SoC）平台进行系统性能观测审计，发现该平台不提供任何CPU功耗计数器、无INA电源轨监测、无IPMI/BMC、也无通过软件接口支持的SCMI powercap协议。唯一可用的能效数据是通过NVML获取的瞬时GPU功耗。进一步发现，联发科固件内部已通过未公开的ACPI接口（SPBM）计算各电源轨能耗，但NVIDIA明确表示‘无计划开放CPU电源轨信息’。因此，基于x86 RAPL实现的单进程能耗归因在该平台无法通过合法接口复现。本文提出能效归因硬件需求规范，设计临时校准桥接方案并在Acer Veriton GN10上验证了其有效性，并提议通过SCMI powercap进入标准化路径。研究呼吁低功耗计算领域将能效可观测性列为首要硬件要求。
原文摘要 · Abstract (English)
Agentic AI workloads - where a single user goal triggers multi-step orchestration, tool calls, retries, and failure recovery - are being targeted for edge deployment, with NVIDIA, Dell, HP, ASUS, MSI, Acer, and Gigabyte all shipping GB10-based desktop AI systems in 2026. Prior work shows orchestration structure dominates agentic energy cost and CPU-side processing accounts for up to 44% of total dynamic energy. We report a systematic energy-observability audit of the ASUS Ascent GX10 (GB10 SoC) and find that the platform exposes no CPU energy counter, no INA power-rail monitor, no IPMI/BMC, and no SCMI powercap protocol through any supported software interface. The only on-device energy telemetry is instantaneous GPU power via NVML. We further discover that the MediaTek firmware already computes per-rail energy internally via an undocumented ACPI interface (SPBM), but NVIDIA states there are "no plans to expose CPU rail information." On-device per-process energy attribution - as performed on x86 via RAPL - is therefore not reproducible on this platform through supported interfaces. We formalize a hardware requirements specification for energy-attributed AI, propose an interim calibration bridge for per-domain energy decomposition - confirmed on the Acer Veriton GN100 where CPU energy accumulators are live - and identify a standards-track path via SCMI powercap. Our findings motivate the low-carbon computing community to demand energy observability as a first-class hardware requirement.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。